Training in progress, step 1000, checkpoint

last-checkpoint/2_Dense/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1a852d6fcae1f2179d5763df7a46fddad1877e145fff513af3347be674ce52b
+oid sha256:00693ca726c3aa172fe54b2bbf0f5a2ac7ef3e0f15e6ef10272ea4e790f1a7ea
 size 9437272

last-checkpoint/3_Dense/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3394c00a0b8299e323b6e83e64ef00be5d726f3c420aa6b111200a304b59f62c
+oid sha256:1ec4b258539975d8b345245718777e000a517241aa23cc10eb37dd6ffc792aab
 size 9437272

last-checkpoint/README.md

@@ -450,7 +450,7 @@ print(query_embeddings.shape, document_embeddings.shape)
 # Get the similarity scores for the embeddings
 similarities = model.similarity(query_embeddings, document_embeddings)
 print(similarities)
-# tensor([[ 0.5962, -0.0191,  0.2550]])
+# tensor([[ 0.4709, -0.1225,  0.1580]])
 ```
 
 <!--
@@ -703,6 +703,10 @@ You can finetune this model on your own dataset.
 | 0.2316 | 700  | 0.1013        |
 | 0.2482 | 750  | 0.1019        |
 | 0.2647 | 800  | 0.0964        |
+| 0.2813 | 850  | 0.0961        |
+| 0.2978 | 900  | 0.0927        |
+| 0.3144 | 950  | 0.0946        |
+| 0.3309 | 1000 | 0.0988        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6ff1bb561b9706f1f8512c3b49593b3ccfe975a3a766ab30ffe85567e0af9d8
+oid sha256:13ac8f3e49e96856b9bc03370f38b3741180dcb037151388805051f7ea3ffe8f
 size 1211486072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:308069358a54642120bbc71415a487f71aebf1cfafc7c73bebd447e79b921486
+oid sha256:45310978fd3a8f93b72bef2a6c703555d44d1cb9ff7e494d4ad2616538a9ff9b
 size 2460923467

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39a64593b8ffcc45b5d5cd6de2eb5cadb176a065ce63970660c524f174fa6360
+oid sha256:fc83c3e7cbaa37ce1778897d2e62cb7b8c41ece6f6ed0596eecff4f3f73fcd86
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7baf2879871f108cbdcd4157b9794e8d6049aec3cf60c7a2c1c3c5259ba4fe4d
+oid sha256:220ab6d106cef455c6160d9f0f26a124a8032f6a0351c6a17f6905e5df60789d
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.26472534745201853,
+  "epoch": 0.3309066843150232,
   "eval_steps": 500,
-  "global_step": 800,
+  "global_step": 1000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -120,6 +120,34 @@
       "learning_rate": 1.6351599852887092e-05,
       "loss": 0.0964,
       "step": 800
+    },
+    {
+      "epoch": 0.2812706816677697,
+      "grad_norm": 6.790607929229736,
+      "learning_rate": 1.5983817579992645e-05,
+      "loss": 0.0961,
+      "step": 850
+    },
+    {
+      "epoch": 0.29781601588352086,
+      "grad_norm": 6.981550693511963,
+      "learning_rate": 1.56160353070982e-05,
+      "loss": 0.0927,
+      "step": 900
+    },
+    {
+      "epoch": 0.314361350099272,
+      "grad_norm": 4.593362808227539,
+      "learning_rate": 1.5248253034203752e-05,
+      "loss": 0.0946,
+      "step": 950
+    },
+    {
+      "epoch": 0.3309066843150232,
+      "grad_norm": 4.783601760864258,
+      "learning_rate": 1.4880470761309307e-05,
+      "loss": 0.0988,
+      "step": 1000
     }
   ],
   "logging_steps": 50,